© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9147
    Prev
    Next
    INDEX
    Explanations

    specific structured data points, particularly in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation (, . ;) or tags (< >)

    np_acts-logits-general · gemini-2.0-flash

    state, error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.49
     Credo
    -0.48
     Immutable
    -0.45
    deprecation
    -0.41
    abancı
    -0.40
     Scu
    -0.40
     développement
    -0.40
     PREL
    -0.39
     Development
    -0.39
     SCI
    -0.39
    POSITIVE LOGITS
    findpost
    0.77
     kasarigan
    0.76
    Архівовано
    0.74
     ostavi
    0.72
     дописавши
    0.72
     createState
    0.70
     createSlice
    0.69
     oprot
    0.68
    ]")]
    0.65
    insee
    0.65
    Activations Density 0.048%

    No Known Activations